This paper presents further development of a compensatory fuzzy model whereby a new set of compensatory factors were defined and a non-normalised version of the model was introduced. The new model was shown to be comparable in many ways with other classical methods such as artificial neural networks and to yield better results. It was also the first to discuss application of the old and enhanced versions of the models in biomedicine. The paper has been widely accepted by the research community whose focus is on the compensatory fuzzy system with/without biomedical application.